© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24577
    Prev
    Next
    INDEX
    Explanations

    easy ui CRUD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ©çī©
    -0.10
     saper
    -0.08
    igh
    -0.08
    stuhl
    -0.08
    æīij
    -0.08
    ogat
    -0.08
    ahari
    -0.08
    åħ¬å®³
    -0.08
    боÑĢом
    -0.08
    @author
    -0.08
    POSITIVE LOGITS
    jÃŃ
    0.06
    äºĭçī©çļĦ
    0.06
    ĭ
    0.06
     Mand
    0.05
    äºĭæĢģ
    0.05
    åħ±åĴĮåĽ½
    0.05
    æŃ¥æŃ¥é«ĺ
    0.05
    stats
    0.05
     k
    0.05
    ç½®
    0.05
    Activations Density 0.652%

    No Known Activations